An approach is provided for adjusting camera shots. The approach involves receiving, via a sensor of a mobile device, an audio signal during a video recording of a subject by a camera of the mobile device. The approach also involves determining, at the mobile device, an audio level in a vicinity of the subject based on the received audio signal, wherein the audio level represents a change in pitch, pace, and cadence of a sound produced by the subject. The approach additionally involves determining that the audio level triggers a shot adjustment state. In the alternative or in addition to, the shot adjustment state is triggered by facial expression of the subject. The approach further involves dynamically adjusting, in response to the shot adjustment state, one or more camera parameters of the camera to alter a shot of the subject by the camera during the video recording. The camera parameters relate to either zoom control, aperture, lighting, or a combination thereof.